{"id":"https://openalex.org/W7204533788","doi":"https://doi.org/10.48550/arxiv.2608.26592","title":"Benchmarking Clinical Decision Pathway Adherence in Large Language Models","display_name":"Benchmarking Clinical Decision Pathway Adherence in Large Language Models","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204533788","doi":"https://doi.org/10.48550/arxiv.2608.26592"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.26592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26592","pdf_url":"https://arxiv.org/pdf/2608.26592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.26592","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148506434","display_name":"Nuo Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Nuo","raw_affiliation_strings":["Fuzhou University Shenzhen Loop","Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University Shenzhen Loop","institution_ids":["https://openalex.org/I80947539"]},{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137770375","display_name":"Xinyang Jiang","orcid":"https://orcid.org/0000-0002-4991-0596","observed_orcids":["https://orcid.org/0000-0002-4991-0596"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xinyang","raw_affiliation_strings":["Area Institute Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Area Institute Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123221288","display_name":"Zilong Wang","orcid":"https://orcid.org/0000-0002-7728-2056","observed_orcids":["https://orcid.org/0000-0002-7728-2056"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zilong","raw_affiliation_strings":["Area Institute Independent Researcher"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Area Institute Independent Researcher","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100626853","display_name":"Zhifei Zhang","orcid":"https://orcid.org/0000-0003-4399-2356","observed_orcids":["https://orcid.org/0000-0003-4399-2356"]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhifei","raw_affiliation_strings":["Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065871371","display_name":"Xiaoye Qu","orcid":"https://orcid.org/0000-0002-4907-3978","observed_orcids":["https://orcid.org/0000-0002-4907-3978"]},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qu, Xiaoye","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081269555","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0002-6834-0322","observed_orcids":["https://orcid.org/0000-0002-6834-0322"]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]},{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng, Jiajun","raw_affiliation_strings":["Tongji University School of Medicine 4 Sun Yat-sen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University School of Medicine 4 Sun Yat-sen","institution_ids":["https://openalex.org/I116953780","https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148512291","display_name":"Yulan Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Yulan","raw_affiliation_strings":["Fuzhou University Shenzhen Loop"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fuzhou University Shenzhen Loop","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064237960","display_name":"Cairong Zhao","orcid":"https://orcid.org/0000-0001-6745-9674","observed_orcids":["https://orcid.org/0000-0001-6745-9674"]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Cairong","raw_affiliation_strings":["Tongji University","University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.002099999925121665,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12664","display_name":"Clinical practice guidelines implementation","score":0.0010999999940395355,"subfield":{"id":"https://openalex.org/subfields/2739","display_name":"Public Health, Environmental and Occupational Health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/clinical-decision-pathway","display_name":"clinical decision pathway","score":0.9829999804496765},{"id":"https://openalex.org/keywords/guideline-adherence","display_name":"guideline adherence","score":0.828000009059906},{"id":"https://openalex.org/keywords/medical-large-language-models","display_name":"medical large language models","score":0.9229999780654907},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.45899999141693115},{"id":"https://openalex.org/keywords/clinical-decision-support","display_name":"clinical decision support","score":0.9589999914169312}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.73089998960495},{"id":"https://openalex.org/C2780182762","wikidata":"https://www.wikidata.org/wiki/Q1630279","display_name":"Guideline","level":2,"score":0.5875999927520752},{"id":"https://openalex.org/C2779974597","wikidata":"https://www.wikidata.org/wiki/Q28448986","display_name":"Clinical Practice","level":2,"score":0.513700008392334},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.4934999942779541},{"id":"https://openalex.org/C9719361","wikidata":"https://www.wikidata.org/wiki/Q7928967","display_name":"Vignette","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C2778373050","wikidata":"https://www.wikidata.org/wiki/Q1774706","display_name":"Clinical pathway","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C63527458","wikidata":"https://www.wikidata.org/wiki/Q5133829","display_name":"Clinical decision support system","level":3,"score":0.4512999951839447},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.43299999833106995},{"id":"https://openalex.org/C107327155","wikidata":"https://www.wikidata.org/wiki/Q330268","display_name":"Decision support system","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4178999960422516},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C2989179672","wikidata":"https://www.wikidata.org/wiki/Q6806500","display_name":"Clinical decision making","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.34709998965263367},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.33739998936653137},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C2982822547","wikidata":"https://www.wikidata.org/wiki/Q179661","display_name":"Medical treatment","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C2993312423","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medical practice","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C19648533","wikidata":"https://www.wikidata.org/wiki/Q691640","display_name":"Evidence-based medicine","level":3,"score":0.25369998812675476},{"id":"https://openalex.org/C2779231881","wikidata":"https://www.wikidata.org/wiki/Q5977147","display_name":"Medical literature","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26592","pdf_url":"https://arxiv.org/pdf/2608.26592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.26592","doi":"https://doi.org/10.48550/arxiv.2608.26592","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26592","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.26592","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26592","pdf_url":"https://arxiv.org/pdf/2608.26592","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8371999859809875,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204533788.pdf","grobid_xml":"https://content.openalex.org/works/W7204533788.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W2501030598","https://openalex.org/W4401306886","https://openalex.org/W4405901456","https://openalex.org/W4414281281","https://openalex.org/W4414458387","https://openalex.org/W4414939355","https://openalex.org/W4415286464","https://openalex.org/W4417086184","https://openalex.org/W4417299769","https://openalex.org/W7075994024","https://openalex.org/W7126256595","https://openalex.org/W7128370680","https://openalex.org/W7141560207"],"related_works":["https://openalex.org/W4417299769","https://openalex.org/W4405321560","https://openalex.org/W7141560207","https://openalex.org/W7162563163","https://openalex.org/W4401752680","https://openalex.org/W7221817050","https://openalex.org/W7161942080","https://openalex.org/W4409654375","https://openalex.org/W7163823375","https://openalex.org/W4391221150"],"abstract_inverted_index":{"Following":[0],"clinical":[1,7,71,80,113],"decision":[2,114],"pathways":[3],"(CDPs)":[4],"defined":[5],"by":[6],"practice":[8,72],"guidelines":[9,60,73],"is":[10,64],"essential":[11],"for":[12,49,101,118,124,132],"safe":[13],"and":[14,69,91,95,127],"reliable":[15,112],"medical":[16,20,52,137],"decision-making.":[17],"However,":[18],"existing":[19],"large":[21],"language":[22],"model":[23],"(LLM)":[24],"benchmarks":[25],"mainly":[26],"evaluate":[27],"final-answer":[28],"accuracy,":[29],"providing":[30],"limited":[31],"evaluation":[32,99,126],"of":[33,130],"models'":[34],"ability":[35],"to":[36,38],"adhere":[37],"guidelines.":[39],"To":[40],"address":[41],"this":[42],"gap,":[43],"we":[44],"introduce":[45],"MEGA-CDP,":[46],"a":[47,75,97],"benchmark":[48],"evaluating":[50],"whether":[51],"LLMs":[53,109],"can":[54],"generate":[55],"guideline-adherent":[56],"CDPs":[57],"using":[58],"provided":[59],"as":[61],"references.":[62],"MEGA-CDP":[63,131],"constructed":[65],"from":[66],"2,274":[67],"English":[68],"Chinese":[70],"through":[74],"guideline-to-case":[76],"pipeline,":[77],"yielding":[78],"42,353":[79],"cases":[81],"with":[82],"explicit":[83],"reference":[84],"CDPs.":[85],"It":[86],"supports":[87],"both":[88],"single-turn":[89],"vignette":[90],"multi-turn":[92],"interactive":[93],"settings,":[94],"introduces":[96],"CDP-oriented":[98,125],"framework":[100],"measuring":[102],"pathway":[103],"consistency.":[104],"Experiments":[105],"on":[106],"16":[107],"representative":[108],"show":[110],"that":[111],"support":[115],"remains":[116],"challenging":[117],"current":[119],"models,":[120],"demonstrating":[121],"the":[122,128],"need":[123],"value":[129],"advancing":[133],"guideline":[134],"adherence":[135],"in":[136],"LLMs.":[138]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}